© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6952
    Prev
    Next
    INDEX
    Explanations

    a variety of coding and mathematical symbols.

    oai_token-act-pair · gemini-2.0-flash

    non-English words or phrases

    np_token-act-pair-logits · gpt-4o-mini

    code and math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.05
    webElementXpaths
    -0.93
     мәкал
    -0.91
    bootstrapcdn
    -0.90
     transfieras
    -0.90
    RenderAtEndOf
    -0.90
     Bioaccumulative
    -0.89
     GenerationType
    -0.89
     mergeFrom
    -0.89
    writeFieldEnd
    -0.88
    POSITIVE LOGITS
     مواليد
    0.54
     Mémoires
    0.44
     piet
    0.42
    itinéraire
    0.42
    ήσει
    0.40
     espres
    0.39
     gloire
    0.39
     misst
    0.39
    ılmıştır
    0.39
    lıyor
    0.36
    Activations Density 7.034%

    No Known Activations